马尔可夫链测试和实施

时间:2010-12-05 19:35:58

标签: c algorithm

所以,我想在随机数字的文本文件中读取并使用这些数字创建后缀列表。它基本上需要使用该算法重现“alice30.txt”中给出的文本。我现在的代码看起来像这样。它编译得很好,但不会为我创建输出文件。我需要反转后缀的数组,以便输出正确。任何帮助将不胜感激。我已经在eprint f头文件中声明了所有必要的函数,比如emalloc。

 #include <string.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
 #include <time.h>
 #include "eprintf.h"

  enum {
NPREF   = 2,    /* number of prefix words */
NHASH   = 4093, /* size of state hash table array */
MAXGEN  = 10000 /* maximum words generated */
   };

 typedef struct State State;
 typedef struct Suffix Suffix;

    struct State {  /* prefix + suffix list */
char    *pref[NPREF];   /* prefix words */
Suffix  *suf;           /* list of suffixes */
State   *next;          /* next in hash table */
    };

   struct Suffix {  /* list of suffixes */
char    *word;          /* suffix */
Suffix  *next;          /* next in list of suffixes */
  };

 State  *lookup(char *prefix[], int create);
 void   build(char *prefix[], FILE* myfile); /*assing the input stream*/
 void       generate(int nwords, int random_num[], FILE* outfile);
  /* passing the array and the output stream*/
 void   add(char *prefix[], char *word);

 State  *statetab[NHASH];   /* hash table of states */

 char NONWORD[] = "\n";  /* cannot appear as real word */


  /* markov main: markov-chain random text generation */
 int main(void)
 {
int i, nwords = MAXGEN;
char *prefix[NPREF];        /* current input prefix */

FILE* random_reader;
FILE* myfile;
FILE* outfile;

int c;
int element;
int random_num[10000];
char* line;
int j=0;
random_reader = fopen("../random_num.txt","r");
myfile = fopen("../alice30.txt","r");
outfile = fopen("../output/markov_c_out.txt","w");
while(fgets(line,20,random_reader)!=NULL)
{
    sscanf(line,"%o",&element);
    random_num[j]= element;
    j++;
}

setprogname("markov");


for (i = 0; i < NPREF; i++) /* set up initial prefix */
    prefix[i] = NONWORD;
build(prefix, myfile);
add(prefix, NONWORD);
generate(nwords, random_num, outfile); // calling the updated function
return 0;
    }   

   const int MULTIPLIER = 31;  /* for hash() */

   /* hash: compute hash value for array of NPREF strings */
     unsigned int hash(char *s[NPREF])
   {
unsigned int h;
unsigned char *p;
int i;

h = 0;
for (i = 0; i < NPREF; i++)
    for (p = (unsigned char *) s[i]; *p != '\0'; p++)
        h = MULTIPLIER * h + *p;
return h % NHASH;
     }

  /* lookup: search for prefix; create if requested. */
   /*  returns pointer if present or created; NULL if not. */
     /*  creation doesn't strdup so strings mustn't change later. */
     State* lookup(char *prefix[NPREF], int create)
   {
int i, h;
State *sp;

h = hash(prefix);
for (sp = statetab[h]; sp != NULL; sp = sp->next) {
    for (i = 0; i < NPREF; i++)
        if (strcmp(prefix[i], sp->pref[i]) != 0)
            break;
    if (i == NPREF)     /* found it */
        return sp;
}
if (create) {
    sp = (State *) emalloc(sizeof(State));
    for (i = 0; i < NPREF; i++)
        sp->pref[i] = prefix[i];
    sp->suf = NULL;
    sp->next = statetab[h];
    statetab[h] = sp;
}
return sp;
      }

     /* addsuffix: add to state. suffix must not change later */
      void addsuffix(State *sp, char *suffix)
     {
Suffix *suf;

suf = (Suffix *) emalloc(sizeof(Suffix));
suf->word = suffix;
suf->next = sp->suf;
sp->suf = suf;
  }

     /* add: add word to suffix list, update prefix */
   void add(char *prefix[NPREF], char *suffix)
    {
State *sp;

sp = lookup(prefix, 1);  /* create if not found */
addsuffix(sp, suffix);
/* move the words down the prefix */
memmove(prefix, prefix+1, (NPREF-1)*sizeof(prefix[0]));
prefix[NPREF-1] = suffix;
        }

       /* build: read input, build prefix table */
         void build(char *prefix[NPREF], FILE *myfile)
        {
char buf[100], fmt[10];

/* create a format string; %s could overflow buf */
sprintf(fmt, "%%%ds", sizeof(buf)-1);
while (fscanf(myfile, fmt, buf) != EOF)
    add(prefix, estrdup(buf));
         }

       /* generate: produce output, one word per line */
     void generate(int nwords, int random_num[], FILE* outfile)
     {
State *sp;
Suffix *suf;
char *prefix[NPREF], *w;
int i, nmatch;

for (i = 0; i < NPREF; i++) /* reset initial prefix */
    prefix[i] = NONWORD;

for (i = 0; i < nwords; i++) {
    sp = lookup(prefix, 0);
    if (sp == NULL)
        eprintf("internal error: lookup failed");
    nmatch = 0;
    for (suf = sp->suf; suf != NULL; suf = suf->next)
        if (random_num[i] % ++nmatch == 0) /*using the elements of the array  */
            w = suf->word;
    if (nmatch == 0)
        eprintf("internal error: no suffix %d %s", i, prefix[0]);
    if (strcmp(w, NONWORD) == 0)
        break;

    fprintf(outfile, w);
    memmove(prefix, prefix+1, (NPREF-1)*sizeof(prefix[0]));
    prefix[NPREF-1] = w;

}

}

2 个答案:

答案 0 :(得分:2)

您正在传递fgets未初始化的变量。

你宣布:

char* line;

以后再打电话:

while(fgets(line,20,random_reader)!=NULL)

但你从未创建空间来存储字符串read。

答案 1 :(得分:0)

除了代码中使用的算法之外,您的程序不会生成输出,因为您没有关闭文件。在主函数的末尾添加以下行:

fclose( outfile );
fclose( myfile );
fclose( randome_reader );

希望这有帮助。